@inproceedings{gezmu-etal-2018-contemporary,
title = "Contemporary {A}mharic Corpus: Automatically Morpho-Syntactically Tagged {A}mharic Corpus",
author = {Gezmu, Andargachew Mekonnen and
Seyoum, Binyam Ephrem and
Gasser, Michael and
N{\"u}rnberger, Andreas},
editor = "Machonis, Peter and
Barreiro, Anabela and
Kocijan, Kristina and
Silberztein, Max",
booktitle = "Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3809",
pages = "65--70",
abstract = "We introduced the contemporary Amharic corpus, which is automatically tagged for morpho-syntactic information. Texts are collected from 25,199 documents from different domains and about 24 million orthographic words are tokenized. Since it is partly a web corpus, we made some automatic spelling error correction. We have also modified the existing morphological analyzer, HornMorpho, to use it for the automatic tagging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gezmu-etal-2018-contemporary">
<titleInfo>
<title>Contemporary Amharic Corpus: Automatically Morpho-Syntactically Tagged Amharic Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andargachew</namePart>
<namePart type="given">Mekonnen</namePart>
<namePart type="family">Gezmu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyam</namePart>
<namePart type="given">Ephrem</namePart>
<namePart type="family">Seyoum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gasser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Nürnberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Machonis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anabela</namePart>
<namePart type="family">Barreiro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Kocijan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Silberztein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduced the contemporary Amharic corpus, which is automatically tagged for morpho-syntactic information. Texts are collected from 25,199 documents from different domains and about 24 million orthographic words are tokenized. Since it is partly a web corpus, we made some automatic spelling error correction. We have also modified the existing morphological analyzer, HornMorpho, to use it for the automatic tagging.</abstract>
<identifier type="citekey">gezmu-etal-2018-contemporary</identifier>
<location>
<url>https://aclanthology.org/W18-3809</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>65</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contemporary Amharic Corpus: Automatically Morpho-Syntactically Tagged Amharic Corpus
%A Gezmu, Andargachew Mekonnen
%A Seyoum, Binyam Ephrem
%A Gasser, Michael
%A Nürnberger, Andreas
%Y Machonis, Peter
%Y Barreiro, Anabela
%Y Kocijan, Kristina
%Y Silberztein, Max
%S Proceedings of the First Workshop on Linguistic Resources for Natural Language Processing
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F gezmu-etal-2018-contemporary
%X We introduced the contemporary Amharic corpus, which is automatically tagged for morpho-syntactic information. Texts are collected from 25,199 documents from different domains and about 24 million orthographic words are tokenized. Since it is partly a web corpus, we made some automatic spelling error correction. We have also modified the existing morphological analyzer, HornMorpho, to use it for the automatic tagging.
%U https://aclanthology.org/W18-3809
%P 65-70
Markdown (Informal)
[Contemporary Amharic Corpus: Automatically Morpho-Syntactically Tagged Amharic Corpus](https://aclanthology.org/W18-3809) (Gezmu et al., LR4NLP 2018)
ACL